© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130278
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶ¾ä¸ĭ
    -0.27
    çī¹æ®Ĭ
    -0.25
    .INSTANCE
    -0.25
    -alist
    -0.25
    éĩĩ
    -0.25
     hôm
    -0.24
     sadd
    -0.24
    对å¤ĸ
    -0.24
    æĭ¿
    -0.23
    åħį
    -0.23
    POSITIVE LOGITS
     variation
    0.27
    â¼¼
    0.27
    alse
    0.27
    aison
    0.26
    ä½ľèĢħæľ¬äºº
    0.25
    BOOLE
    0.25
    arl
    0.25
    midd
    0.25
     house
    0.24
    饰æ¼Ķ
    0.24
    Activations Density 7.308%

    No Known Activations